AI-Assisted Detection and Staging of Gastric Cancer Using Contrast-Enhanced CT

Nanjing Medical University

Status: Enrolling

Conditions: Gastric Cancer Stage; Gastric Cancer Patients Undergoing Gastrectomy

Treatments: Diagnostic Test: CT scan

Study type: Observational

Funder types: Other

Identifiers

NCT07250347

2025-SR-842

Details and patient eligibility

About

Accurate preoperative assessment of gastric cancer stage guides eligibility for endoscopic resection, extent of gastrectomy and lymphadenectomy, selection for neoadjuvant therapy, and use of staging laparoscopy. Contrast-enhanced CT (CECT) is guideline-endorsed for initial staging, yet performance varies across institutions and readers. This study will evaluate an artificial-intelligence (AI) system that analyzes routine CECT to detect gastric cancer and assign four-class T stage (T1-T4) and N stage (N0-N3) .

Full description

Adults with confirmed gastric cancer undergoing pre-treatment CECT will be enrolled. The AI analysis will be applied to clinically acquired images. Radiologist interpretations with and without AI support will be collected in a prespecified reader study. The reference standard will include surgical pathology, supplemented by clinical follow-up when applicable. The primary outcome is detection performance, diagnostic performance of the AI for four-class staging (e.g., accuracy and area under the receiver operating characteristic curve). Secondary outcomes include the effect of AI assistance on reader accuracy and interpretation time, inter-reader agreement, and cross-site reproducibility.

Enrollment: 8,000 estimated patients

Sex: All

Ages: 18 to 85 years old

Volunteers: No Healthy Volunteers

Inclusion criteria

1. pathologically confirmed gastric cancer;
2. preoperative contrast-enhanced CT performed;
3. no evidence of distant metastasis on baseline staging;
4. curative-intent management with complete postoperative histopathology.

Exclusion criteria

1. prior treatment before surgery;
2. non-diagnostic or poor-quality CT precluding evaluation.

Trial design

8,000 participants in 3 patient groups

Cohort 1 (Internal Derivation Cohort)

Description:

Retrospective case-only cohort of adults with pathologically confirmed gastric cancer who underwent preoperative contrast-enhanced CT at the sponsoring institution. Existing CT images and clinical/pathology records will be used to train and test the AI model and to estimate diagnostic performance for T and N staging.

Treatment:

Diagnostic Test: CT scan

Cohort 2 (External Validation Cohort A)

Description:

Independent retrospective case-only cohort from an external hospital with the same inclusion/exclusion criteria. Used solely for external validation to assess reproducibility across sites and scanners.

Treatment:

Diagnostic Test: CT scan

Cohort 3 (External Validation Cohort B)

Description:

A second independent retrospective validation cohort from another institution to further test generalizability.

Treatment:

Diagnostic Test: CT scan